ClawHub
Back to skill

Security audit

DACHSER

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed DACHSER connector helper that uses the OOMOL CLI for shipment and delivery-order queries, with no hidden persistence or unrelated behavior found.

Install only if you intend to let an agent use your connected OOMOL DACHSER account. Review payloads before any action marked [write], and treat the CLI install/login steps as recovery steps to run only when needed.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The skill labels `get_delivery_order_status` as a `[write]` action even though its name and description indicate a status-retrieval operation. This kind of schema/documentation mismatch is dangerous because it can cause an agent or operator to mis-handle the action's risk, either by avoiding legitimate reads or, worse, by normalizing inaccurate safety metadata around state-changing operations in a skill that can read, create, and update DACHSER data.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description says to use this skill for ANY DACHSER request and instead of calling the API directly, creating an overly broad activation scope. This increases the chance the skill is invoked for loosely related requests, causing unnecessary access to a connected enterprise system and raising the risk of unintended data exposure or execution of sensitive operations under ambiguous user intent.

Static analysis

No suspicious patterns detected.